基于KL距离和双密度小波变换的纹理图像检索

为了进一步提纹理图像的检索性能，提出了一种基于双密度小波的算法。该算法根据双密度小波分解的特点。从系数角度出发首先进行子带组合，然后提取子带小波系数直方图分布特性作为纹理特征。利用最大似然估计规则将特征提取和相似计算结合起来．采用KL距离进行度量．与单小波和双密度小波方法比较．该算法具有时移不变性、特证数少等特点。理论分析和纹理图像检索的对比实验数据说明了组合双密度小波在纹理特征提取方面的性能优于单小波和双密度小波。检索率分别提高了。

Texture Image Retrieval Based Complex Wavelet and KL Distance

In order to enhance the performance of the texture image retrieval, a new method based on the complex wavelet transform (CWT) was presented, which had obtained by the statistical characteristics of the complex wavelet transform (CWT) real and image part from the wavelet coefficient histogram distribution as the texture feature using the characteristics of the complex wavelet decomposition and combining feature extraction with similarity measurement by ML rule using KL distance for image retrieval. In comparison with the traditional wavelet, this method is better than these of the pyramid discrete wavelet decomposition transforms (PDWT) under the same feature extraction method and the same similarity measure. In the contrast experiment result for image retrieval, the retrieval efficiency of the CWT is better than that of the PDWT and the efficiency of Kingsbury's method is superior than that of Fernandes's within the CWT in the texture retrieval.